this post was submitted on 25 Feb 2025
1 points (100.0% liked)

Phys.org

314 readers
1 users here now

Phys.org internet news portal provides the latest news on science including: Physics, Nanotechnology, Life Sciences, Space Science, Earth Science, Environment, Health and Medicine.

founded 1 year ago
MODERATORS
bot@rss.ponder.cat
admin@rss.ponder.cat
free@rss.ponder.cat
PhilipTheBucket@ponder.cat
1
Automatic cell analysis: AI-powered software 'segments anything' in microscopy images (phys.org)
submitted 6 months ago by free@rss.ponder.cat to c/phys@rss.ponder.cat
1 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] homesweethomeMrL@lemmy.world 1 points 6 months ago

It was already possible to carry out automatic segmentation of those biological structures, but the dedicated methods only worked in specific conditions and adapting them to new conditions was costly. An international research team led by Göttingen University has now developed a method for retraining the existing AI-based software Segment Anything on over 17,000 microscopy images with over 2 million structures annotated by hand.

So getting the AI to spit back the work already done and hope it doesn't hallucinate something so everything has to be double-checked anyway? Ok I guess.